Joel Oskarsson

Selected publications

1. 

   Probabilistic Weather Forecasting with Hierarchical Graph Neural Networks

   Joel Oskarsson, Tomas Landelius, Marc Peter Deisenroth, and Fredrik Lindsten

   In Advances in Neural Information Processing Systems 2024

   Spotlight

   Abs Bib PDF Code

   In recent years, machine learning has established itself as a powerful tool for high-resolution weather forecasting. While most current machine learning models focus on deterministic forecasts, accurately capturing the uncertainty in the chaotic weather system calls for probabilistic modeling. We propose a probabilistic weather forecasting model called Graph-EFM, combining a flexible latent-variable formulation with the successful graph-based forecasting framework. The use of a hierarchical graph construction allows for efficient sampling of spatially coherent forecasts. Requiring only a single forward pass per time step, Graph-EFM allows for fast generation of arbitrarily large ensembles. We experiment with the model on both global and limited area forecasting. Ensemble forecasts from Graph-EFM achieve equivalent or lower errors than comparable deterministic models, with the added benefit of accurately capturing forecast uncertainty.

   @inproceedings{oskarsson2024probabilistic,
     title = {Probabilistic Weather Forecasting with Hierarchical Graph Neural Networks},
     author = {Oskarsson, Joel and Landelius, Tomas and Deisenroth, Marc Peter and Lindsten, Fredrik},
     year = {2024},
     booktitle = {Advances in Neural Information Processing Systems},
     volume = {37},
   }

2. 

   Temporal Graph Neural Networks for Irregular Data

   Joel Oskarsson, Per Sidén, and Fredrik Lindsten

   In Proceedings of The 26th International Conference on Artificial Intelligence and Statistics 2023

   Abs Bib PDF Video Code Poster Slides

   This paper proposes a temporal graph neural network model for forecasting of graph-structured irregularly observed time series. Our TGNN4I model is designed to handle both irregular time steps and partial observations of the graph. This is achieved by introducing a time-continuous latent state in each node, following a linear Ordinary Differential Equation (ODE) defined by the output of a Gated Recurrent Unit (GRU). The ODE has an explicit solution as a combination of exponential decay and periodic dynamics. Observations in the graph neighborhood are taken into account by integrating graph neural network layers in both the GRU state update and predictive model. The time-continuous dynamics additionally enable the model to make predictions at arbitrary time steps. We propose a loss function that leverages this and allows for training the model for forecasting over different time horizons. Experiments on simulated data and real-world data from traffic and climate modeling validate the usefulness of both the graph structure and time-continuous dynamics in settings with irregular observations.

   @inproceedings{tgnn4i,
     title = {Temporal Graph Neural Networks for Irregular Data},
     author = {Oskarsson, Joel and Sid\'en, Per and Lindsten, Fredrik},
     booktitle = {Proceedings of The 26th International Conference on Artificial Intelligence and Statistics},
     pages = {4515--4531},
     year = {2023},
     editor = {Ruiz, Francisco and Dy, Jennifer and van de Meent, Jan-Willem},
     volume = {206},
     series = {Proceedings of Machine Learning Research},
     publisher = {PMLR},
   }

3. 

   Scalable Deep Gaussian Markov Random Fields for General Graphs

   Joel Oskarsson, Per Sidén, and Fredrik Lindsten

   In Proceedings of the 39th International Conference on Machine Learning 2022

   Abs Bib PDF Video Code Poster Slides

   Machine learning methods on graphs have proven useful in many applications due to their ability to handle generally structured data. The framework of Gaussian Markov Random Fields (GMRFs) provides a principled way to define Gaussian models on graphs by utilizing their sparsity structure. We propose a flexible GMRF model for general graphs built on the multi-layer structure of Deep GMRFs, originally proposed for lattice graphs only. By designing a new type of layer we enable the model to scale to large graphs. The layer is constructed to allow for efficient training using variational inference and existing software frameworks for Graph Neural Networks. For a Gaussian likelihood, close to exact Bayesian inference is available for the latent field. This allows for making predictions with accompanying uncertainty estimates. The usefulness of the proposed model is verified by experiments on a number of synthetic and real world datasets, where it compares favorably to other both Bayesian and deep learning methods.

   @inproceedings{pmlr-v162-oskarsson22a,
     title = {Scalable Deep {G}aussian {M}arkov Random Fields for General Graphs},
     author = {Oskarsson, Joel and Sid{\'e}n, Per and Lindsten, Fredrik},
     booktitle = {Proceedings of the 39th International Conference on Machine Learning},
     pages = {17117--17137},
     year = {2022},
     editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan},
     volume = {162},
     series = {Proceedings of Machine Learning Research},
     publisher = {PMLR},
   }